BA-Net: Brightness prior guided attention network for colonic polyp segmentation

被引:4
|
作者
Xia, Haiying [1 ]
Qin, Yilin [1 ]
Tan, Yumei [2 ]
Song, Shuxiang [1 ]
机构
[1] Guangxi Normal Univ, Coll Elect Engn, Guilin 541004, Peoples R China
[2] Guangxi Normal Univ, Sch Comp Sci & Engn, Guilin 541004, Peoples R China
关键词
Deep learning; Computer-aided diagnosis; Colonic polyp segmentation; Global reverse attention; Brightness prior knowledge;
D O I
10.1016/j.bbe.2023.08.001
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Automatic polyp segmentation at colonoscopy plays an important role in the early diagno-sis and surgery of colorectal cancer. However, the diversity of polyps in different images greatly increases the difficulty of accurately segmenting polyps. Manual segmentation of polyps in colonoscopic images is time-consuming and the rate of polyps missed remains high. In this paper, we propose a brightness prior guided attention network (BA-Net) for automatic polyp segmentation. Specifically, we first aggregate the high-level features of the last three layers of the encoder with an enhanced receptive field (ERF) module, which further fed to the decoder to obtain the initial prediction maps. Then, we introduce a brightness prior fusion (BF) module that fuses the brightness prior information into the multi-scale side-out high-level semantic features. The BF module aims to induce the net-work to localize salient regions, which may be potential polyps, to obtain better segmenta-tion results. Finally, we propose a global reverse attention (GRA) module to combine the output of the BF module and the initial prediction map for obtaining long-range depen-dence and reverse refinement prediction results. With iterative refinement from higher-level semantics to lower-level semantics, our BA-Net can achieve more refined and accu-rate segmentation. Extensive experiments show that our BA-Net outperforms the state -of-the-art methods on six common polyp datasets.& COPY; 2023 Nalecz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences. Published by Elsevier B.V. All rights reserved.
引用
收藏
页码:603 / 615
页数:13
相关论文
共 50 条
  • [31] Toward accurate polyp segmentation with cascade boundary-guided attention
    Huilin Lai
    Ye Luo
    Guokai Zhang
    Xiaoang Shen
    Bo Li
    Jianwei Lu
    The Visual Computer, 2023, 39 : 1453 - 1469
  • [32] RCNU-Net: Reparameterized convolutional network with convolutional block attention module for improved polyp image segmentation
    Huang, Boxiong
    Huang, Tongyuan
    Xu, Jia
    Min, Jie
    Hu, Chuanxin
    Zhang, Zhixing
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2024, 93
  • [33] CSUnet: a dual attention and hybrid convolutional network for polyp segmentation
    Liu, Shangwang
    Si, Feiyan
    Lin, Yinghai
    SIGNAL IMAGE AND VIDEO PROCESSING, 2024, 18 (11) : 8445 - 8456
  • [34] MSRAformer: Multiscale spatial reverse attention network for polyp segmentation
    Wu, Cong
    Long, Cheng
    Li, Shijun
    Yang, Junjie
    Jiang, Fagang
    Zhou, Ran
    COMPUTERS IN BIOLOGY AND MEDICINE, 2022, 151
  • [35] MACNet: Multi-Attention and Context Network for Polyp Segmentation
    Hao, Xiuzhen
    Pan, Haiwei
    Zhang, Kejia
    Chen, Chunling
    Bian, Xiaofei
    He, Shuning
    WEB AND BIG DATA, PT II, APWEB-WAIM 2022, 2023, 13422 : 369 - 384
  • [36] DCANet: deep context attention network for automatic polyp segmentation
    Zaka-Ud-Din Muhammad
    Zhangjin Huang
    Naijie Gu
    Usman Muhammad
    The Visual Computer, 2023, 39 : 5513 - 5525
  • [37] DCANet: deep context attention network for automatic polyp segmentation
    Muhammad, Zaka-Ud-Din
    Huang, Zhangjin
    Gu, Naijie
    Muhammad, Usman
    VISUAL COMPUTER, 2022,
  • [38] Shared Hybrid Attention Transformer network for colon polyp segmentation
    Ji, Zexuan
    Qian, Hao
    Ma, Xiao
    NEUROCOMPUTING, 2025, 616
  • [39] DCANet: deep context attention network for automatic polyp segmentation
    Muhammad, Zaka-Ud-Din
    Huang, Zhangjin
    Gu, Naijie
    Muhammad, Usman
    VISUAL COMPUTER, 2023, 39 (11): : 5513 - 5525
  • [40] Polyp Segmentation Network Combined With Multi-Attention Mechanism
    Jia L.
    Hu Y.
    Jin Y.
    Xue Z.
    Jiang Z.
    Zheng Q.
    Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics, 2023, 35 (03): : 463 - 473